INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tuk

-0.16

eyh

-0.16

 jadx

-0.15

/feed

-0.15

 GenÃ§

-0.15

tors

-0.14

ahren

-0.14

 Cust

-0.14

ä¾Ľ

-0.14

ojis

-0.14

POSITIVE LOGITS

clr

0.15

angen

0.14

elif

0.14

.elapsed

0.14

fax

0.14

 signed

0.13

sic

0.13

Î©Î£

0.13

ëĿ½

0.13

iloc

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.